Skeleton to Abstraction: An Attentive Information Extraction Schema for Enhancing the Saliency of Text Summarization

Skeleton to Abstraction: An Attentive Information Extraction Schema for Enhancing the Saliency of Text Summarization

Current popular abstractive summarization is based on an attentional encoder-decoder framework. Based on the architecture, the decoder generates a summary according to the full text that often results in the decoder being interfered by some irrelevant information, thereby causing the generated summa...

Full description

Bibliographic Details
Main Authors: Xiujuan Xiang, Guangluan Xu, Xingyu Fu, Yang Wei, Li Jin, Lei Wang
Format: Article
Language:English
Published: MDPI AG 2018-08-01
Series:Information
Subjects:
recurrent neural network (RNN)
abstractive text summarization
information extraction
attention mechanism
semantic relevance
saliency of summarization
Online Access:http://www.mdpi.com/2078-2489/9/9/217

Internet

http://www.mdpi.com/2078-2489/9/9/217

Similar Items